VFM-Det: Towards High-Performance Vehicle Detection via Large Foundation Models

TL;DR

VFM-Det introduces a novel vehicle detection method leveraging a pre-trained vehicle model and large language models to enhance detection accuracy by aligning semantic attributes with visual features.

Contribution

The paper proposes VFM-Det, a new vehicle detection framework that integrates a pre-trained vehicle model and semantic attribute prediction to improve detection performance.

Findings

Achieved +5.1% AP_{0.5} on Cityscapes

Achieved +6.2% AP_{0.75} on Cityscapes

Demonstrated effectiveness across three benchmark datasets

Abstract

Existing vehicle detectors are usually obtained by training a typical detector (e.g., YOLO, RCNN, DETR series) on vehicle images based on a pre-trained backbone (e.g., ResNet, ViT). Some researchers also exploit and enhance the detection performance using pre-trained large foundation models. However, we think these detectors may only get sub-optimal results because the large models they use are not specifically designed for vehicles. In addition, their results heavily rely on visual features, and seldom of they consider the alignment between the vehicle's semantic information and visual representations. In this work, we propose a new vehicle detection paradigm based on a pre-trained foundation vehicle model (VehicleMAE) and a large language model (T5), termed VFM-Det. It follows the region proposal-based detection framework and the features of each proposal can be enhanced using VehicleMAE. More importantly, we propose a new VAtt2Vec module that predicts the vehicle semantic attributes of these proposals and transforms them into feature vectors to enhance the vision features via contrastive learning. Extensive experiments on three vehicle detection benchmark datasets thoroughly proved the effectiveness of our vehicle detector. Specifically, our model improves the baseline approach by $+5.1\%$, $+6.2\%$ on the $AP_{0.5}$, $AP_{0.75}$ metrics, respectively, on the Cityscapes dataset.The source code of this work will be released at https://github.com/Event-AHU/VFM-Det.